{"skill":{"slug":"aiml-voice","displayName":"AIML Voice Transcript","summary":"Transcribe audio files (ogg, mp3, wav, etc.) using AIMLAPI. Use when the user provides audio messages or local audio files. Provides a reliable Python script...","description":"---\nname: aimlapi-voice\ndescription: Transcribe audio files (ogg, mp3, wav, etc.) using AIMLAPI. Use when the user provides audio messages or local audio files. Provides a reliable Python script with retries and polling.\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"🎙️\",\n        \"requires\": { \"bins\": [\"python\"], \"env\": [\"AIMLAPI_API_KEY\"] },\n        \"primaryEnv\": \"AIMLAPI_API_KEY\",\n      },\n  }\n---\n\n# AIMLAPI Voice Transcription\n\n## Overview\n\nA robust skill for transcribing audio via AIMLAPI's specialized speech-to-text endpoints. It handles queuing, polling for results, and automatic MIME-type detection.\n\n## Quick Start\n\n```bash\n# Set your API key first (if not in env)\n# export AIMLAPI_API_KEY=\"your-key-here\"\n\n# Transcribe a file\npython {baseDir}/scripts/transcribe.py path/to/audio.ogg\n```\n\n## Tasks\n\n### Process Voice Messages\n\nWhen an audio file is received, use this script to extract the text.\n\n```bash\npython {baseDir}/scripts/transcribe.py <file_path> \\\n  --model \"#g1_whisper-medium\" \\\n  --verbose\n```\n\n### Arguments\n\n- `file`: (Required) Path to the audio file.\n- `--model`: Model ID (default: `#g1_whisper-medium`).\n- `--out`: Path to save the transcript text.\n- `--poll-interval`: Seconds between status checks (default: 5).\n- `--max-wait`: Stop waiting after N seconds (default: 300).\n\n## Dependencies\n\n- Python 3\n- `AIMLAPI_API_KEY` set in environment or provided via `--apikey-file`.\n","topics":["Transcription","Audio"],"tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":646,"installsAllTime":24,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1772121156192,"updatedAt":1778491652688},"latestVersion":{"version":"1.0.0","createdAt":1772121156192,"changelog":"Initial release of AIMLAPI audio transcription skill.\n\n- Transcribes audio files (ogg, mp3, wav, etc.) using AIMLAPI's speech-to-text endpoints.\n- Supports robust queuing, polling for results, and automatic MIME-type detection.\n- CLI script for submitting, tracking, and saving transcription output.\n- Requires AIMLAPI_API_KEY.\n- Adjustable model, polling interval, and timeout options.","license":null},"metadata":{"setup":[{"key":"AIMLAPI_API_KEY","required":true}],"os":null,"systems":null},"owner":{"handle":"aimlapihello","userId":"s17drvcvgge2x0ywnxqd5n3v8n884z0t","displayName":"AI/ML API","image":"https://avatars.githubusercontent.com/u/187510884?v=4"},"moderation":null}